.. _sec_sentiment_rnn:
感情分析: 再帰型ニューラルネットワークの使用
============================================
単語類似度や類推のタスクと同様に、
感情分析にも事前学習済みの単語ベクトルを適用できる。
:numref:`sec_sentiment` の IMDb レビューデータセットは
それほど大きくないため、 大規模コーパスで事前学習された
テキスト表現を用いることで、 モデルの過学習を抑えられる可能性がある。
:numref:`fig_nlp-map-sa-rnn` に示す具体例では、 各トークンを
事前学習済みの GloVe モデルで表現し、 それらのトークン表現を 多層双方向
RNN に入力して テキスト系列表現を得る。 その表現は
感情分析の出力へと変換される :cite:`Maas.Daly.Pham.ea.2011`\ 。
同じ下流アプリケーションに対して、 後ほど別のアーキテクチャ上の
選択肢も検討する。
.. _fig_nlp-map-sa-rnn:
.. figure:: ../img/nlp-map-sa-rnn.svg
この節では、事前学習済み GloVe を RNN
ベースの感情分析アーキテクチャに入力する。
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
from d2l import torch as d2l
import torch
from torch import nn
batch_size = 64
train_iter, test_iter, vocab = d2l.load_data_imdb(batch_size)
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
from d2l import mxnet as d2l
from mxnet import gluon, init, np, npx
from mxnet.gluon import nn, rnn
npx.set_np()
batch_size = 64
train_iter, test_iter, vocab = d2l.load_data_imdb(batch_size)
.. raw:: latex
\diilbookstyleoutputcell
.. parsed-literal::
:class: output
Downloading ../data/aclImdb_v1.tar.gz from http://d2l-data.s3-accelerate.amazonaws.com/aclImdb_v1.tar.gz...
[07:03:42] ../src/storage/storage.cc:196: Using Pooled (Naive) StorageManager for CPU
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
embed_size, num_hiddens, num_layers, devices = 100, 100, 2, d2l.try_all_gpus()
net = BiRNN(len(vocab), embed_size, num_hiddens, num_layers)
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
embed_size, num_hiddens, num_layers, devices = 100, 100, 2, d2l.try_all_gpus()
net = BiRNN(len(vocab), embed_size, num_hiddens, num_layers)
.. raw:: html
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
class BiRNN(nn.Module):
def __init__(self, vocab_size, embed_size, num_hiddens,
num_layers, **kwargs):
super(BiRNN, self).__init__(**kwargs)
self.embedding = nn.Embedding(vocab_size, embed_size)
# Set `bidirectional` to True to get a bidirectional RNN
self.encoder = nn.LSTM(embed_size, num_hiddens, num_layers=num_layers,
bidirectional=True)
self.decoder = nn.Linear(4 * num_hiddens, 2)
def forward(self, inputs):
# The shape of `inputs` is (batch size, no. of time steps). Because
# LSTM requires its input's first dimension to be the temporal
# dimension, the input is transposed before obtaining token
# representations. The output shape is (no. of time steps, batch size,
# word vector dimension)
embeddings = self.embedding(inputs.T)
self.encoder.flatten_parameters()
# Returns hidden states of the last hidden layer at different time
# steps. The shape of `outputs` is (no. of time steps, batch size,
# 2 * no. of hidden units)
outputs, _ = self.encoder(embeddings)
# Concatenate the hidden states at the initial and final time steps as
# the input of the fully connected layer. Its shape is (batch size,
# 4 * no. of hidden units)
encoding = torch.cat((outputs[0], outputs[-1]), dim=1)
outs = self.decoder(encoding)
return outs
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
class BiRNN(nn.Block):
def __init__(self, vocab_size, embed_size, num_hiddens,
num_layers, **kwargs):
super(BiRNN, self).__init__(**kwargs)
self.embedding = nn.Embedding(vocab_size, embed_size)
# Set `bidirectional` to True to get a bidirectional RNN
self.encoder = rnn.LSTM(num_hiddens, num_layers=num_layers,
bidirectional=True, input_size=embed_size)
self.decoder = nn.Dense(2)
def forward(self, inputs):
# The shape of `inputs` is (batch size, no. of time steps). Because
# LSTM requires its input's first dimension to be the temporal
# dimension, the input is transposed before obtaining token
# representations. The output shape is (no. of time steps, batch size,
# word vector dimension)
embeddings = self.embedding(inputs.T)
# Returns hidden states of the last hidden layer at different time
# steps. The shape of `outputs` is (no. of time steps, batch size,
# 2 * no. of hidden units)
outputs = self.encoder(embeddings)
# Concatenate the hidden states at the initial and final time steps as
# the input of the fully connected layer. Its shape is (batch size,
# 4 * no. of hidden units)
encoding = np.concatenate((outputs[0], outputs[-1]), axis=1)
outs = self.decoder(encoding)
return outs
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
glove_embedding = d2l.TokenEmbedding('glove.6b.100d')
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
glove_embedding = d2l.TokenEmbedding('glove.6b.100d')
.. raw:: html
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
embed_size, num_hiddens, num_layers, devices = 100, 100, 2, d2l.try_all_gpus()
net = BiRNN(len(vocab), embed_size, num_hiddens, num_layers)
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
embed_size, num_hiddens, num_layers, devices = 100, 100, 2, d2l.try_all_gpus()
net = BiRNN(len(vocab), embed_size, num_hiddens, num_layers)
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
embeds = glove_embedding[vocab.idx_to_token]
embeds.shape
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
embeds = glove_embedding[vocab.idx_to_token]
embeds.shape
.. raw:: html
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
def init_weights(module):
if type(module) == nn.Linear:
nn.init.xavier_uniform_(module.weight)
if type(module) == nn.LSTM:
for param in module._flat_weights_names:
if "weight" in param:
nn.init.xavier_uniform_(module._parameters[param])
net.apply(init_weights);
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
net.initialize(init.Xavier(), ctx=devices)
.. raw:: latex
\diilbookstyleoutputcell
.. parsed-literal::
:class: output
[07:03:48] ../src/storage/storage.cc:196: Using Pooled (Naive) StorageManager for GPU
[07:03:48] ../src/storage/storage.cc:196: Using Pooled (Naive) StorageManager for GPU
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
predict_sentiment(net, vocab, 'this movie is so great')
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
predict_sentiment(net, vocab, 'this movie is so great')
.. raw:: html
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
glove_embedding = d2l.TokenEmbedding('glove.6b.100d')
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
glove_embedding = d2l.TokenEmbedding('glove.6b.100d')
.. raw:: latex
\diilbookstyleoutputcell
.. parsed-literal::
:class: output
Downloading ../data/glove.6B.100d.zip from http://d2l-data.s3-accelerate.amazonaws.com/glove.6B.100d.zip...
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
predict_sentiment(net, vocab, 'this movie is so bad')
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
predict_sentiment(net, vocab, 'this movie is so bad')
.. raw:: html
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
net.embedding.weight.data.copy_(embeds)
net.embedding.weight.requires_grad = False
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
net.embedding.weight.set_data(embeds)
net.embedding.collect_params().setattr('grad_req', 'null')
.. raw:: html
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
lr, num_epochs = 0.01, 5
trainer = torch.optim.Adam(net.parameters(), lr=lr)
loss = nn.CrossEntropyLoss(reduction="none")
d2l.train_ch13(net, train_iter, test_iter, loss, trainer, num_epochs, devices)
.. raw:: latex
\diilbookstyleoutputcell
.. parsed-literal::
:class: output
loss 0.295, train acc 0.877, test acc 0.848
2845.4 examples/sec on [device(type='cuda', index=0), device(type='cuda', index=1)]
.. figure:: output_sentiment-analysis-rnn_e3f486_88_1.svg
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
lr, num_epochs = 0.01, 5
trainer = gluon.Trainer(net.collect_params(), 'adam', {'learning_rate': lr})
loss = gluon.loss.SoftmaxCrossEntropyLoss()
d2l.train_ch13(net, train_iter, test_iter, loss, trainer, num_epochs, devices)
.. raw:: latex
\diilbookstyleoutputcell
.. parsed-literal::
:class: output
loss 0.291, train acc 0.877, test acc 0.854
747.8 examples/sec on [gpu(0), gpu(1)]
.. figure:: output_sentiment-analysis-rnn_e3f486_91_1.svg
.. raw:: html
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
#@save
def predict_sentiment(net, vocab, sequence):
"""Predict the sentiment of a text sequence."""
sequence = torch.tensor(vocab[sequence.split()], device=d2l.try_gpu())
label = torch.argmax(net(sequence.reshape(1, -1)), dim=1)
return 'positive' if label == 1 else 'negative'
.. raw:: html
.. raw:: html
.. raw:: latex
\diilbookstyleinputcell
.. code:: python
#@save
def predict_sentiment(net, vocab, sequence):
"""Predict the sentiment of a text sequence."""
sequence = np.array(vocab[sequence.split()], ctx=d2l.try_gpu())
label = np.argmax(net(sequence.reshape(1, -1)), axis=1)
return 'positive' if label == 1 else 'negative'
.. raw:: html
.. raw:: html